To determine the DGE profiles (for mouse genes), relative to uninfected controls, of self-assembling co-cultures of primary human hepatocytes (SACC-PHHs) mono-infected with HBV or co-infected with HBV/HDV at 8 and 28 days post-infection. This run includes the samples sequenced in July 2018.
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(stringr)
library(ggplot2)
library(reshape2)
library(openxlsx)
library(DESeq2)
## Loading required package: S4Vectors
## Loading required package: stats4
## Loading required package: BiocGenerics
## Loading required package: parallel
##
## Attaching package: 'BiocGenerics'
## The following objects are masked from 'package:parallel':
##
## clusterApply, clusterApplyLB, clusterCall, clusterEvalQ,
## clusterExport, clusterMap, parApply, parCapply, parLapply,
## parLapplyLB, parRapply, parSapply, parSapplyLB
## The following objects are masked from 'package:dplyr':
##
## combine, intersect, setdiff, union
## The following objects are masked from 'package:stats':
##
## IQR, mad, xtabs
## The following objects are masked from 'package:base':
##
## anyDuplicated, append, as.data.frame, cbind, colnames,
## do.call, duplicated, eval, evalq, Filter, Find, get, grep,
## grepl, intersect, is.unsorted, lapply, lengths, Map, mapply,
## match, mget, order, paste, pmax, pmax.int, pmin, pmin.int,
## Position, rank, rbind, Reduce, rownames, sapply, setdiff,
## sort, table, tapply, union, unique, unsplit, which, which.max,
## which.min
##
## Attaching package: 'S4Vectors'
## The following objects are masked from 'package:dplyr':
##
## first, rename
## The following objects are masked from 'package:base':
##
## colMeans, colSums, expand.grid, rowMeans, rowSums
## Loading required package: IRanges
##
## Attaching package: 'IRanges'
## The following objects are masked from 'package:dplyr':
##
## collapse, desc, slice
## Loading required package: GenomicRanges
## Loading required package: GenomeInfoDb
## Loading required package: SummarizedExperiment
## Loading required package: Biobase
## Welcome to Bioconductor
##
## Vignettes contain introductory material; view with
## 'browseVignettes()'. To cite Bioconductor, see
## 'citation("Biobase")', and for packages 'citation("pkgname")'.
library(gplots)
##
## Attaching package: 'gplots'
## The following object is masked from 'package:IRanges':
##
## space
## The following object is masked from 'package:S4Vectors':
##
## space
## The following object is masked from 'package:stats':
##
## lowess
library(dplyr)
library(RColorBrewer)
library(stringr)
library(genefilter)
library(data.table)
##
## Attaching package: 'data.table'
## The following object is masked from 'package:SummarizedExperiment':
##
## shift
## The following object is masked from 'package:GenomicRanges':
##
## shift
## The following object is masked from 'package:IRanges':
##
## shift
## The following objects are masked from 'package:S4Vectors':
##
## first, second
## The following objects are masked from 'package:reshape2':
##
## dcast, melt
## The following objects are masked from 'package:dplyr':
##
## between, first, last
library(genefilter)
library(ggrepel)
library(viridis)
## Loading required package: viridisLite
source("http://bioconductor.org/biocLite.R")
## Bioconductor version 3.4 (BiocInstaller 1.24.0), ?biocLite for help
## A new version of Bioconductor is available after installing the most
## recent version of R; see http://bioconductor.org/install
biocLite("org.Mm.eg.db")
## BioC_mirror: https://bioconductor.org
## Using Bioconductor 3.4 (BiocInstaller 1.24.0), R 3.3.3 (2017-03-06).
## Installing package(s) 'org.Mm.eg.db'
## installing the source package 'org.Mm.eg.db'
## Old packages: 'ape', 'callr', 'carData', 'chron', 'cli', 'cluster',
## 'data.table', 'dendextend', 'devtools', 'digest', 'doBy', 'doParallel',
## 'dplyr', 'evaluate', 'fansi', 'ggplot2', 'ggthemes', 'hexbin',
## 'htmlwidgets', 'igraph', 'kernlab', 'later', 'maptools', 'MASS',
## 'Matrix', 'mclust', 'mgcv', 'mime', 'mvtnorm', 'nleqslv', 'nloptr',
## 'pkgconfig', 'processx', 'R6', 'Rcpp', 'RcppArmadillo', 'reprex',
## 'reshape', 'rlang', 'robustbase', 'rstudioapi', 'scales', 'seriation',
## 'snow', 'survival', 'testthat', 'tidyr', 'tidyselect', 'tinytex',
## 'webshot', 'WGCNA', 'xfun', 'XML', 'xtable'
require(org.Mm.eg.db)
## Loading required package: org.Mm.eg.db
## Loading required package: AnnotationDbi
##
## Attaching package: 'AnnotationDbi'
## The following object is masked from 'package:dplyr':
##
## select
##
Function to perform DGE analysis with both donor and treatment set as factors influencing the counts.
DGE_analysis <- function(sampledirectory) {
a <- basename(Sys.glob(file.path(sampledirectory, "*.txt")))
sample_names <- sub('.txt', '', a)
##Here the donors are renamed based off the Hurel names (i.e. HU___) - RNASeq reads were all
##named using a different ID system.
sampleTable <- data.frame(sampleName = sample_names, sampleFile = a, treatment =
ifelse(grepl("Ctrl", a), "mock", ifelse(grepl("*co|*HDV", a),"coinf", "HBV")),
donor = ifelse(grepl("BD330*", a), "HU1019",
ifelse(grepl("BD405*", a), "HU1020",
ifelse(grepl("HU1016*", a), "HU1016", "HU1007"))),
time = ifelse(grepl("*D8|Day 8", a), "d8", "d28"),
replicate = ifelse(grepl("*sample_1h|*D8_ah|*D8_aa|*D8_am|*sample_1m", a), "a",
ifelse(grepl("*sample_2h|D28_bh|D28_ba|D28_bm|*sample_2m", a), "b",
ifelse(grepl("*sample_3h| * sample 1h|* sample 1m", a), "c",
ifelse(grepl("* sample 2h|* sample 2m", a), "d",
ifelse(grepl("* sample 3h|* sample 3m", a), "e", ""))))))
dds <- DESeqDataSetFromHTSeqCount(sampleTable = sampleTable, directory = sampledirectory,
design = ~donor + treatment)
dds
dds@colData
contrast <- c("treatment", levels(sampleTable$treatment))
output_basename <- sprintf("%s-%s_vs_%s_%s_analysis", "Mousegenes", contrast[2],
contrast[3], levels(sampleTable$time))
output_basename
dds <- estimateSizeFactors(dds)
dds@colData
dds <- estimateDispersions(dds)
plotDispEsts(dds, main=sprintf("%s Dispersion Estimates", output_basename))
dds <- nbinomWaldTest(dds)
res <- results(dds, contrast=contrast)
res <- res[order(res$padj, -abs(res$log2FoldChange)),]
mcols(res, use.names=TRUE)
##Log-intensity ratios = M values, log-intensity averages = A values
##Red points indicate padj < 0.1.
plotMA(res, alpha=0.1, main=sprintf(output_basename))
attr(res, "filterThreshold")
metadata(res)$alpha
metadata(res)$filterThreshold
plot(metadata(res)$filterNumRej,
type="b", ylab="number of rejections",
xlab="quantiles of filter")
lines(metadata(res)$lo.fit, col="red")
abline(v=metadata(res)$filterTheta)
key = "ENSEMBL"
cols = c("ENTREZID", "SYMBOL", "GENENAME", "ALIAS", "REFSEQ", "ACCNUM")
for (col in cols) {
# Get annotation data for column
annotation_data <- AnnotationDbi::select(org.Mm.eg.db, rownames(res), col, keytype=key)
# Collapse one-to-many relationships
tmp <- aggregate(annotation_data[col], by=annotation_data[key],
# to a list
FUN=function(x)list(x))
# Match on key and append to results
idx <- match(rownames(res), tmp[[key]])
res[[col]] <- tmp[idx,col]
}
output_data <- as.data.frame(res)
LIST_COLS <- sapply(output_data, is.list)
for (COL in colnames(output_data)[LIST_COLS]) {
output_data[COL] <-
sapply(output_data[COL],
function(x)sapply(x, function(y) paste(unlist(y),
collapse=", ") ) )
}
# Save data frame above as tab-separated file
write.table(output_data,
file=file.path("Mouse DGEs_donortreatment", paste(Sys.Date(),
"mouse_donor_treatment",output_basename, "_results.txt", sep='')),
quote=FALSE, sep="\t", row.names=TRUE, col.names=NA)
return(list(dds@colData, head(res)))
}
##For each timepoint, determine the DGE profile when comparing the different treatments
##groups to one another (i.e. HBV-infected versus control).
##uninfected control cells versus those mono-infected with HBV
DGE_analysis("Mouse d8_ctrlvHBV")
## gene-wise dispersion estimates
## mean-dispersion relationship
## final dispersion estimates
## 'select()' returned 1:many mapping between keys and columns
## 'select()' returned 1:many mapping between keys and columns
## 'select()' returned 1:many mapping between keys and columns
## 'select()' returned 1:many mapping between keys and columns
## 'select()' returned 1:many mapping between keys and columns
## 'select()' returned 1:many mapping between keys and columns
## [[1]]
## DataFrame with 12 rows and 5 columns
## treatment donor time replicate
## <factor> <factor> <factor> <factor>
## BD330_Ctrl_D8mousegenes mock HU1019 d8
## BD330_HBV_D8mousegenes HBV HU1019 d8
## BD405A_Ctrl_D8mousegenes mock HU1020 d8
## BD405A_HBV_D8mousegenes HBV HU1020 d8
## Ctrl_D8_sample_1mousegenes mock HU1007 d8 a
## ... ... ... ... ...
## HBV_D8_sample_1mousegenes HBV HU1007 d8 a
## HBV_D8_sample_2mousegenes HBV HU1007 d8 b
## HBV_D8_sample_3mousegenes HBV HU1007 d8
## HU1016 Ctrl D8mousegenes mock HU1016 d8
## HU1016_B_D8mousegenes HBV HU1016 d8
## sizeFactor
## <numeric>
## BD330_Ctrl_D8mousegenes 1.0522833
## BD330_HBV_D8mousegenes 0.7382776
## BD405A_Ctrl_D8mousegenes 0.7851726
## BD405A_HBV_D8mousegenes 0.7187235
## Ctrl_D8_sample_1mousegenes 1.1914770
## ... ...
## HBV_D8_sample_1mousegenes 1.4504736
## HBV_D8_sample_2mousegenes 0.9846915
## HBV_D8_sample_3mousegenes 1.4119102
## HU1016 Ctrl D8mousegenes 0.8937149
## HU1016_B_D8mousegenes 0.8234693
##
## [[2]]
## log2 fold change (MAP): treatment HBV vs mock
## Wald test p-value: treatment HBV vs mock
## DataFrame with 6 rows and 12 columns
## baseMean log2FoldChange lfcSE stat
## <numeric> <numeric> <numeric> <numeric>
## ENSMUSG00000035385 1320.3139 -0.9589377 0.1549593 -6.188318
## ENSMUSG00000039518 6501.1613 0.8093483 0.1512841 5.349858
## ENSMUSG00000036144 243.2058 -1.0747784 0.2074015 -5.182114
## ENSMUSG00000027792 923.9060 -1.0579783 0.2040122 -5.185858
## ENSMUSG00000022231 1628.0571 -0.8301908 0.1675028 -4.956281
## ENSMUSG00000031072 202.3899 0.6575575 0.1438225 4.572006
## pvalue padj ENTREZID SYMBOL
## <numeric> <numeric> <list> <list>
## ENSMUSG00000035385 6.080937e-10 6.764435e-06 20296 Ccl2
## ENSMUSG00000039518 8.802331e-08 4.895856e-04 386463 Cdsn
## ENSMUSG00000036144 2.193852e-07 6.101101e-04 17286 Meox2
## ENSMUSG00000027792 2.150227e-07 6.101101e-04 12038 Bche
## ENSMUSG00000022231 7.185525e-07 1.598636e-03 20356 Sema5a
## ENSMUSG00000031072 4.830778e-06 8.956263e-03 72284 Oraov1
## GENENAME
## <list>
## ENSMUSG00000035385 chemokine (C-C motif) ligand 2
## ENSMUSG00000039518 corneodesmosin
## ENSMUSG00000036144 mesenchyme homeobox 2
## ENSMUSG00000027792 butyrylcholinesterase
## ENSMUSG00000022231 sema domain, seven thrombospondin repeats (type 1 and type 1-like), transmembrane domain (TM) and short cytoplasmic domain, (semaphorin) 5A
## ENSMUSG00000031072 oral cancer overexpressed 1
## ALIAS
## <list>
## ENSMUSG00000035385 AI323594,HC11,JE,...
## ENSMUSG00000039518 AI747712,Cdsn
## ENSMUSG00000036144 AI528662,Gax,Mox-2,...
## ENSMUSG00000027792 C730038G20Rik,Bche
## ENSMUSG00000022231 5930434A13,9130201M22Rik,AI464145,...
## ENSMUSG00000031072 2210010N10Rik,TAOS1,Oraov1
## REFSEQ
## <list>
## ENSMUSG00000035385 NM_011333,NP_035463
## ENSMUSG00000039518 NM_001008424,NP_001008424,XM_006524543,...
## ENSMUSG00000036144 NM_008584,NP_032610
## ENSMUSG00000027792 NM_009738,NP_033868,XM_011240000,...
## ENSMUSG00000022231 NM_009154,NP_033180,XM_006520043,...
## ENSMUSG00000031072 NM_028184,NP_082460,XM_006508649,...
## ACCNUM
## <list>
## ENSMUSG00000035385 AAA37684,AAA37685,AAF15379,...
## ENSMUSG00000039518 AA562785,AAH55373,AK133029,...
## ENSMUSG00000036144 AAH02076,AAP32018,AK028352,...
## ENSMUSG00000027792 AAA37328,AAH99977,AK050337,...
## ENSMUSG00000022231 AAH65137,AK031231,AK033613,...
## ENSMUSG00000031072 AAH06906,AAH13564,AAO13812,...
DGE_analysis("Mouse d28_ctrlvHBV")
## gene-wise dispersion estimates
## mean-dispersion relationship
## final dispersion estimates
## 'select()' returned 1:many mapping between keys and columns
## 'select()' returned 1:many mapping between keys and columns
## 'select()' returned 1:many mapping between keys and columns
## 'select()' returned 1:many mapping between keys and columns
## 'select()' returned 1:many mapping between keys and columns
## 'select()' returned 1:many mapping between keys and columns
## [[1]]
## DataFrame with 12 rows and 5 columns
## treatment donor time replicate
## <factor> <factor> <factor> <factor>
## BD330_Ctrl_D28mousegenes mock HU1019 d28
## BD330_HBV_D28mousegenes HBV HU1019 d28
## BD405A_Ctrl_D28mousegenes mock HU1020 d28
## BD405A_HBV_D28mousegenes HBV HU1020 d28
## Ctrl_D28_sample_1mousegenes mock HU1007 d28 a
## ... ... ... ... ...
## HBV_D28_sample_1mousegenes HBV HU1007 d28 a
## HBV_D28_sample_2mousegenes HBV HU1007 d28 b
## HBV_D28_sample_3mousegenes HBV HU1007 d28
## HU1016 Ctrl D28mousegenes mock HU1016 d28
## HU1016_B_D28mousegenes HBV HU1016 d28
## sizeFactor
## <numeric>
## BD330_Ctrl_D28mousegenes 1.3009710
## BD330_HBV_D28mousegenes 0.5694832
## BD405A_Ctrl_D28mousegenes 1.1260174
## BD405A_HBV_D28mousegenes 0.8927813
## Ctrl_D28_sample_1mousegenes 0.6416672
## ... ...
## HBV_D28_sample_1mousegenes 1.1035405
## HBV_D28_sample_2mousegenes 1.2618667
## HBV_D28_sample_3mousegenes 0.8042829
## HU1016 Ctrl D28mousegenes 1.7595897
## HU1016_B_D28mousegenes 1.1915768
##
## [[2]]
## log2 fold change (MAP): treatment HBV vs mock
## Wald test p-value: treatment HBV vs mock
## DataFrame with 6 rows and 12 columns
## baseMean log2FoldChange lfcSE stat
## <numeric> <numeric> <numeric> <numeric>
## ENSMUSG00000029838 4846.94016 0.9185637 0.1641840 5.594720
## ENSMUSG00000074934 775.80079 -0.6098879 0.1236597 -4.931984
## ENSMUSG00000021596 103.32692 -0.8101245 0.1735435 -4.668136
## ENSMUSG00000024913 8130.06210 0.5824642 0.1353846 4.302293
## ENSMUSG00000064341 27893.63028 0.4607397 0.1107244 4.161138
## ENSMUSG00000028718 70.92816 -0.7083442 0.1799058 -3.937307
## pvalue padj ENTREZID SYMBOL
## <numeric> <numeric> <list> <list>
## ENSMUSG00000029838 2.209784e-08 0.0004980411 19242 Ptn
## ENSMUSG00000074934 8.139841e-07 0.0091727868 23892 Grem1
## ENSMUSG00000021596 3.039451e-06 0.0228343796 78771 Mctp1
## ENSMUSG00000024913 1.690392e-05 0.0952451526 16973 Lrp5
## ENSMUSG00000064341 3.166653e-05 0.1427400355 17716 ND1
## ENSMUSG00000028718 8.240102e-05 0.2908543705 20460 Stil
## GENENAME
## <list>
## ENSMUSG00000029838 pleiotrophin
## ENSMUSG00000074934 gremlin 1, DAN family BMP antagonist
## ENSMUSG00000021596 multiple C2 domains, transmembrane 1
## ENSMUSG00000024913 low density lipoprotein receptor-related protein 5
## ENSMUSG00000064341 NADH dehydrogenase subunit 1
## ENSMUSG00000028718 Scl/Tal1 interrupting locus
## ALIAS
## <list>
## ENSMUSG00000029838 HARP,HB-GAM,HBBN,...
## ENSMUSG00000074934 Cktsf1b1,Drm,Grem,...
## ENSMUSG00000021596 2810465F10Rik,Mctp1
## ENSMUSG00000024913 BMND1,HBM,LR3,...
## ENSMUSG00000064341 ND1
## ENSMUSG00000028718 Sil,Stil
## REFSEQ
## <list>
## ENSMUSG00000029838 NM_008973,NP_032999,XM_006505757,...
## ENSMUSG00000074934 NM_011824,NP_035954,XM_006499444,...
## ENSMUSG00000021596 NM_030174,NP_084450,XM_006517462,...
## ENSMUSG00000024913 NM_008513,NP_032539,XR_388250
## ENSMUSG00000064341 NP_904328
## ENSMUSG00000028718 NM_001304551,NM_001304553,NM_001304555,...
## ACCNUM
## <list>
## ENSMUSG00000029838 AAB21834,AAH02064,AAH61695,...
## ENSMUSG00000074934 AAC40111,AAD54056,AAD54057,...
## ENSMUSG00000021596 AK013379,AK047562,AK054478,...
## ENSMUSG00000024913 AAC36468,AAC70183,AAH11374,...
## ENSMUSG00000064341 AAN85122,AAP89023,AAR21195,...
## ENSMUSG00000028718 AAC52386,AAH04585,AAH49865,...
##uninfected control cells versus those co-infected with HBV and HDV
DGE_analysis("Mouse d8_ctrlvcoinf")
## gene-wise dispersion estimates
## mean-dispersion relationship
## final dispersion estimates
## 'select()' returned 1:many mapping between keys and columns
## 'select()' returned 1:many mapping between keys and columns
## 'select()' returned 1:many mapping between keys and columns
## 'select()' returned 1:many mapping between keys and columns
## 'select()' returned 1:many mapping between keys and columns
## 'select()' returned 1:many mapping between keys and columns
## [[1]]
## DataFrame with 16 rows and 5 columns
## treatment donor time
## <factor> <factor> <factor>
## BD330 HBV_HDV Day 8 sample 1mousegenes coinf HU1019 d8
## BD330 HBV_HDV Day 8 sample 2mousegenes coinf HU1019 d8
## BD330 HBV_HDV Day 8 sample 3mousegenes coinf HU1019 d8
## BD330_Ctrl_D8mousegenes mock HU1019 d8
## BD330_HBV_HDV_D8_amousegenes coinf HU1019 d8
## ... ... ... ...
## Ctrl_D8_sample_1mousegenes mock HU1007 d8
## Ctrl_D8_sample_2mousegenes mock HU1007 d8
## Ctrl_D8_sample_3mousegenes mock HU1007 d8
## HU1016 Ctrl D8mousegenes mock HU1016 d8
## HU1016_BD_co_D8mousegenes coinf HU1016 d8
## replicate sizeFactor
## <factor> <numeric>
## BD330 HBV_HDV Day 8 sample 1mousegenes c 0.8269965
## BD330 HBV_HDV Day 8 sample 2mousegenes d 0.8982170
## BD330 HBV_HDV Day 8 sample 3mousegenes e 0.6922215
## BD330_Ctrl_D8mousegenes 1.2863206
## BD330_HBV_HDV_D8_amousegenes a 0.7531468
## ... ... ...
## Ctrl_D8_sample_1mousegenes a 1.438224
## Ctrl_D8_sample_2mousegenes b 1.621194
## Ctrl_D8_sample_3mousegenes 1.387785
## HU1016 Ctrl D8mousegenes 1.116317
## HU1016_BD_co_D8mousegenes 1.061993
##
## [[2]]
## log2 fold change (MAP): treatment coinf vs mock
## Wald test p-value: treatment coinf vs mock
## DataFrame with 6 rows and 12 columns
## baseMean log2FoldChange lfcSE stat
## <numeric> <numeric> <numeric> <numeric>
## ENSMUSG00000036158 219.08223 1.1711543 0.1847361 6.339606
## ENSMUSG00000038393 6158.30436 -0.8535824 0.1753516 -4.867833
## ENSMUSG00000050578 215.43878 -1.0891644 0.2352736 -4.629352
## ENSMUSG00000021750 73.55790 1.0797301 0.2336259 4.621620
## ENSMUSG00000026475 62.05723 -1.0034907 0.2166718 -4.631385
## ENSMUSG00000000392 5.78075 -0.8571356 0.1836560 -4.667070
## pvalue padj ENTREZID SYMBOL
## <numeric> <numeric> <list> <list>
## ENSMUSG00000036158 2.303542e-10 3.989044e-06 106042 Prickle1
## ENSMUSG00000038393 1.128288e-06 9.769278e-03 56338 Txnip
## ENSMUSG00000050578 3.668122e-06 1.098925e-02 17386 Mmp13
## ENSMUSG00000021750 3.807559e-06 1.098925e-02 268709 Fam107a
## ENSMUSG00000026475 3.632279e-06 1.098925e-02 19734 Rgs16
## ENSMUSG00000000392 3.055248e-06 1.098925e-02 14089 Fap
## GENENAME
## <list>
## ENSMUSG00000036158 prickle planar cell polarity protein 1
## ENSMUSG00000038393 thioredoxin interacting protein
## ENSMUSG00000050578 matrix metallopeptidase 13
## ENSMUSG00000021750 family with sequence similarity 107, member A
## ENSMUSG00000026475 regulator of G-protein signaling 16
## ENSMUSG00000000392 fibroblast activation protein
## ALIAS
## <list>
## ENSMUSG00000036158 1110058P22Rik,AW215793,Prickle,...
## ENSMUSG00000038393 1200008J08Rik,AA682105,Hyplip1,...
## ENSMUSG00000050578 Clg,MMP-13,Mmp1,...
## ENSMUSG00000021750 DRR1,Fam107a
## ENSMUSG00000026475 Rgs14,Rgsr,Rgs16
## ENSMUSG00000000392 SIMP,Fap
## REFSEQ
## <list>
## ENSMUSG00000036158 NM_001033217,NP_001028389,XM_006520264,...
## ENSMUSG00000038393 NM_001009935,NM_023719,NP_001009935,...
## ENSMUSG00000050578 NM_008607,NP_032633
## ENSMUSG00000021750 NM_183187,NP_899010,XM_006518019,...
## ENSMUSG00000026475 NM_011267,NP_035397
## ENSMUSG00000000392 NM_007986,NP_032012,XM_006498746,...
## ACCNUM
## <list>
## ENSMUSG00000036158 AAH23970,AAI17893,AAI17894,...
## ENSMUSG00000038393 AAD48499,AAG32665,AAG32666,...
## ENSMUSG00000050578 AAI25321,AAI25323,AAT46404,...
## ENSMUSG00000021750 AAH55107,AK044219,AK083253,...
## ENSMUSG00000026475 AAB50619,AAC16913,AAC52927,...
## ENSMUSG00000000392 AAH19190,AK051959,AK136578,...
DGE_analysis("Mouse d28_ctrlvcoinf")
## gene-wise dispersion estimates
## mean-dispersion relationship
## final dispersion estimates
## 'select()' returned 1:many mapping between keys and columns
## 'select()' returned 1:many mapping between keys and columns
## 'select()' returned 1:many mapping between keys and columns
## 'select()' returned 1:many mapping between keys and columns
## 'select()' returned 1:many mapping between keys and columns
## 'select()' returned 1:many mapping between keys and columns
## [[1]]
## DataFrame with 16 rows and 5 columns
## treatment donor time
## <factor> <factor> <factor>
## BD330 HBV_HDV Day 28 sample 1mousegenes coinf HU1019 d28
## BD330 HBV_HDV Day 28 sample 2mousegenes coinf HU1019 d28
## BD330 HBV_HDV Day 28 sample 3mousegenes coinf HU1019 d28
## BD330_Ctrl_D28mousegenes mock HU1019 d28
## BD330_HBV_HDV_D28_bmousegenes coinf HU1019 d28
## ... ... ... ...
## Ctrl_D28_sample_1mousegenes mock HU1007 d28
## Ctrl_D28_sample_2mousegenes mock HU1007 d28
## Ctrl_D28_sample_3mousegenes mock HU1007 d28
## HU1016 Ctrl D28mousegenes mock HU1016 d28
## HU1016_BD_co_D28mousegenes coinf HU1016 d28
## replicate sizeFactor
## <factor> <numeric>
## BD330 HBV_HDV Day 28 sample 1mousegenes c 0.8988611
## BD330 HBV_HDV Day 28 sample 2mousegenes d 1.0578876
## BD330 HBV_HDV Day 28 sample 3mousegenes e 1.1254465
## BD330_Ctrl_D28mousegenes 1.2183718
## BD330_HBV_HDV_D28_bmousegenes b 1.1926363
## ... ... ...
## Ctrl_D28_sample_1mousegenes a 0.5782738
## Ctrl_D28_sample_2mousegenes b 0.9196221
## Ctrl_D28_sample_3mousegenes 0.9683076
## HU1016 Ctrl D28mousegenes 1.6579823
## HU1016_BD_co_D28mousegenes 0.9963621
##
## [[2]]
## log2 fold change (MAP): treatment coinf vs mock
## Wald test p-value: treatment coinf vs mock
## DataFrame with 6 rows and 12 columns
## baseMean log2FoldChange lfcSE stat
## <numeric> <numeric> <numeric> <numeric>
## ENSMUSG00000033491 147.01899 0.9227285 0.1992539 4.630919
## ENSMUSG00000026399 128.08315 0.9116428 0.2194460 4.154293
## ENSMUSG00000017493 1706.66225 -0.8752717 0.2075056 -4.218063
## ENSMUSG00000037820 126.63093 -0.8425417 0.2011891 -4.187810
## ENSMUSG00000106944 19.85382 0.7458254 0.1785755 4.176527
## ENSMUSG00000038963 83.01172 0.7544383 0.1889308 3.993200
## pvalue padj ENTREZID SYMBOL
## <numeric> <numeric> <list> <list>
## ENSMUSG00000033491 3.640456e-06 0.08107295 244954 Prss35
## ENSMUSG00000026399 3.262953e-05 0.14533192 13136 Cd55
## ENSMUSG00000017493 2.464101e-05 0.14533192 16010 Igfbp4
## ENSMUSG00000037820 2.816595e-05 0.14533192 21817 Tgm2
## ENSMUSG00000106944 2.959930e-05 0.14533192 NA NA
## ENSMUSG00000038963 6.518753e-05 0.24195438 108115 Slco4a1
## GENENAME
## <list>
## ENSMUSG00000033491 protease, serine 35
## ENSMUSG00000026399 CD55 molecule, decay accelerating factor for complement
## ENSMUSG00000017493 insulin-like growth factor binding protein 4
## ENSMUSG00000037820 transglutaminase 2, C polypeptide
## ENSMUSG00000106944 NA
## ENSMUSG00000038963 solute carrier organic anion transporter family, member 4a1
## ALIAS
## <list>
## ENSMUSG00000033491 6030424L22Rik,P3D9,Prss35
## ENSMUSG00000026399 Daf,Daf-GPI,Daf1,...
## ENSMUSG00000017493 AI875747,Deb2,IGFBP-4,...
## ENSMUSG00000037820 G[a]h,TG2,TGase2,...
## ENSMUSG00000106944 NA
## ENSMUSG00000038963 OATP-E,Slc21a12,Slco4a1
## REFSEQ
## <list>
## ENSMUSG00000033491 NM_178738,NP_848853,XM_006511170,...
## ENSMUSG00000026399 NM_010016,NP_034146,XM_006529115,...
## ENSMUSG00000017493 NM_010517,NP_034647
## ENSMUSG00000037820 NM_009373,NP_033399
## ENSMUSG00000106944 NA
## ENSMUSG00000038963 NM_148933,NP_683735,XM_006500547,...
## ACCNUM
## <list>
## ENSMUSG00000033491 AAH75675,ABB46197,AK030671,...
## ENSMUSG00000026399 AAB00091,AAD51447,AAD51449,...
## ENSMUSG00000017493 AAH19836,AK003243,AK031212,...
## ENSMUSG00000037820 AAA40420,AAC62014,AAD37501,...
## ENSMUSG00000106944 NA
## ENSMUSG00000038963 AAH30719,AAH30720,AAH33602,...
##monoinfected cells (HBV only) versus those co-infected with HBV and HDV
DGE_analysis("Mouse d8_coinfvHBV")
## gene-wise dispersion estimates
## mean-dispersion relationship
## final dispersion estimates
## 'select()' returned 1:many mapping between keys and columns
## 'select()' returned 1:many mapping between keys and columns
## 'select()' returned 1:many mapping between keys and columns
## 'select()' returned 1:many mapping between keys and columns
## 'select()' returned 1:many mapping between keys and columns
## 'select()' returned 1:many mapping between keys and columns
## [[1]]
## DataFrame with 16 rows and 5 columns
## treatment donor time
## <factor> <factor> <factor>
## BD330 HBV_HDV Day 8 sample 1mousegenes coinf HU1019 d8
## BD330 HBV_HDV Day 8 sample 2mousegenes coinf HU1019 d8
## BD330 HBV_HDV Day 8 sample 3mousegenes coinf HU1019 d8
## BD330_HBV_D8mousegenes HBV HU1019 d8
## BD330_HBV_HDV_D8_amousegenes coinf HU1019 d8
## ... ... ... ...
## HBV_D8_sample_1mousegenes HBV HU1007 d8
## HBV_D8_sample_2mousegenes HBV HU1007 d8
## HBV_D8_sample_3mousegenes HBV HU1007 d8
## HU1016_BD_co_D8mousegenes coinf HU1016 d8
## HU1016_B_D8mousegenes HBV HU1016 d8
## replicate sizeFactor
## <factor> <numeric>
## BD330 HBV_HDV Day 8 sample 1mousegenes c 0.8517347
## BD330 HBV_HDV Day 8 sample 2mousegenes d 0.9272059
## BD330 HBV_HDV Day 8 sample 3mousegenes e 0.7144467
## BD330_HBV_D8mousegenes 0.9254134
## BD330_HBV_HDV_D8_amousegenes a 0.7785908
## ... ... ...
## HBV_D8_sample_1mousegenes a 1.795777
## HBV_D8_sample_2mousegenes b 1.226536
## HBV_D8_sample_3mousegenes 1.762998
## HU1016_BD_co_D8mousegenes 1.100822
## HU1016_B_D8mousegenes 1.024806
##
## [[2]]
## log2 fold change (MAP): treatment coinf vs HBV
## Wald test p-value: treatment coinf vs HBV
## DataFrame with 6 rows and 12 columns
## baseMean log2FoldChange lfcSE stat
## <numeric> <numeric> <numeric> <numeric>
## ENSMUSG00000034115 52.84019 2.3885023 0.3142402 7.600880
## ENSMUSG00000036144 401.07299 2.0072207 0.2903875 6.912214
## ENSMUSG00000028760 201.71111 -1.1454251 0.1958018 -5.849922
## ENSMUSG00000038393 5942.75005 -0.8608777 0.1535069 -5.608073
## ENSMUSG00000027875 88.99761 -1.6093765 0.2939548 -5.474912
## ENSMUSG00000048489 94.70841 -1.5419523 0.2955123 -5.217896
## pvalue padj ENTREZID SYMBOL
## <numeric> <numeric> <list> <list>
## ENSMUSG00000034115 2.941230e-14 4.367727e-10 24046 Scn11a
## ENSMUSG00000036144 4.771466e-12 3.542813e-08 17286 Meox2
## ENSMUSG00000028760 4.918026e-09 2.434423e-05 230861 Eif4g3
## ENSMUSG00000038393 2.045918e-08 7.595471e-05 56338 Txnip
## ENSMUSG00000027875 4.377286e-08 1.300054e-04 15360 Hmgcs2
## ENSMUSG00000048489 1.809667e-07 4.478925e-04 213393 8430408G22Rik
## GENENAME
## <list>
## ENSMUSG00000034115 sodium channel, voltage-gated, type XI, alpha
## ENSMUSG00000036144 mesenchyme homeobox 2
## ENSMUSG00000028760 eukaryotic translation initiation factor 4 gamma, 3
## ENSMUSG00000038393 thioredoxin interacting protein
## ENSMUSG00000027875 3-hydroxy-3-methylglutaryl-Coenzyme A synthase 2
## ENSMUSG00000048489 RIKEN cDNA 8430408G22 gene
## ALIAS
## <list>
## ENSMUSG00000034115 NSS2,NaN,NaT,...
## ENSMUSG00000036144 AI528662,Gax,Mox-2,...
## ENSMUSG00000028760 1500002J22Rik,4833436O05,4930523M17Rik,...
## ENSMUSG00000038393 1200008J08Rik,AA682105,Hyplip1,...
## ENSMUSG00000027875 1300002P16,mHS,Hmgcs2
## ENSMUSG00000048489 Depp,Fseg,8430408G22Rik
## REFSEQ
## <list>
## ENSMUSG00000034115 NM_011887,NP_036017,XM_017313362,...
## ENSMUSG00000036144 NM_008584,NP_032610
## ENSMUSG00000028760 NM_001256195,NM_001256198,NM_172703,...
## ENSMUSG00000038393 NM_001009935,NM_023719,NP_001009935,...
## ENSMUSG00000027875 NM_008256,NP_032282
## ENSMUSG00000048489 NM_001166580,NM_145980,NP_001160052,...
## ACCNUM
## <list>
## ENSMUSG00000034115 AAD53403,AAO85711,AB031389,...
## ENSMUSG00000036144 AAH02076,AAP32018,AK028352,...
## ENSMUSG00000028760 AAH23898,AAH47531,AAH48848,...
## ENSMUSG00000038393 AAD48499,AAG32665,AAG32666,...
## ENSMUSG00000027875 AAA92675,AAA92676,AAH14714,...
## ENSMUSG00000048489 AAH31533,AAH58515,AB024924,...
DGE_analysis("Mouse d28_coinfvHBV")
## gene-wise dispersion estimates
## mean-dispersion relationship
## final dispersion estimates
## 'select()' returned 1:many mapping between keys and columns
## 'select()' returned 1:many mapping between keys and columns
## 'select()' returned 1:many mapping between keys and columns
## 'select()' returned 1:many mapping between keys and columns
## 'select()' returned 1:many mapping between keys and columns
## 'select()' returned 1:many mapping between keys and columns
## [[1]]
## DataFrame with 16 rows and 5 columns
## treatment donor time
## <factor> <factor> <factor>
## BD330 HBV_HDV Day 28 sample 1mousegenes coinf HU1019 d28
## BD330 HBV_HDV Day 28 sample 2mousegenes coinf HU1019 d28
## BD330 HBV_HDV Day 28 sample 3mousegenes coinf HU1019 d28
## BD330_HBV_D28mousegenes HBV HU1019 d28
## BD330_HBV_HDV_D28_bmousegenes coinf HU1019 d28
## ... ... ... ...
## HBV_D28_sample_1mousegenes HBV HU1007 d28
## HBV_D28_sample_2mousegenes HBV HU1007 d28
## HBV_D28_sample_3mousegenes HBV HU1007 d28
## HU1016_BD_co_D28mousegenes coinf HU1016 d28
## HU1016_B_D28mousegenes HBV HU1016 d28
## replicate sizeFactor
## <factor> <numeric>
## BD330 HBV_HDV Day 28 sample 1mousegenes c 0.9545548
## BD330 HBV_HDV Day 28 sample 2mousegenes d 1.1207982
## BD330 HBV_HDV Day 28 sample 3mousegenes e 1.1965253
## BD330_HBV_D28mousegenes 0.5608572
## BD330_HBV_HDV_D28_bmousegenes b 1.2679145
## ... ... ...
## HBV_D28_sample_1mousegenes a 1.0801663
## HBV_D28_sample_2mousegenes b 1.2219894
## HBV_D28_sample_3mousegenes 0.7671387
## HU1016_BD_co_D28mousegenes 1.0579929
## HU1016_B_D28mousegenes 1.1896661
##
## [[2]]
## log2 fold change (MAP): treatment coinf vs HBV
## Wald test p-value: treatment coinf vs HBV
## DataFrame with 6 rows and 12 columns
## baseMean log2FoldChange lfcSE stat
## <numeric> <numeric> <numeric> <numeric>
## ENSMUSG00000049093 36.18814 2.326889 0.3518473 6.613351
## ENSMUSG00000027656 485.45875 -2.049403 0.3242750 -6.319953
## ENSMUSG00000037370 128.75418 1.842799 0.3010990 6.120242
## ENSMUSG00000018830 86.33487 -1.803739 0.3054746 -5.904709
## ENSMUSG00000006014 55.49869 -1.990055 0.3455553 -5.759006
## ENSMUSG00000026822 1405.67824 -1.841151 0.3274374 -5.622911
## pvalue padj ENTREZID SYMBOL
## <numeric> <numeric> <list> <list>
## ENSMUSG00000049093 3.757163e-11 5.184133e-07 209590 Il23r
## ENSMUSG00000027656 2.616426e-10 1.805072e-06 22403 Wisp2
## ENSMUSG00000037370 9.343331e-10 4.297309e-06 18605 Enpp1
## ENSMUSG00000018830 3.532690e-09 1.218601e-05 17880 Myh11
## ENSMUSG00000006014 8.461072e-09 2.334917e-05 96875 Prg4
## ENSMUSG00000026822 1.877663e-08 4.317999e-05 16819 Lcn2
## GENENAME
## <list>
## ENSMUSG00000049093 interleukin 23 receptor
## ENSMUSG00000027656 WNT1 inducible signaling pathway protein 2
## ENSMUSG00000037370 ectonucleotide pyrophosphatase/phosphodiesterase 1
## ENSMUSG00000018830 myosin, heavy polypeptide 11, smooth muscle
## ENSMUSG00000006014 proteoglycan 4 (megakaryocyte stimulating factor, articular superficial zone protein)
## ENSMUSG00000026822 lipocalin 2
## ALIAS
## <list>
## ENSMUSG00000049093 IL-23R,Il23r
## ENSMUSG00000027656 Ccn5,Crgr4,Ctgfl,...
## ENSMUSG00000037370 4833416E15Rik,AI428932,C76301,...
## ENSMUSG00000018830 AV071570,SM1,SM2,...
## ENSMUSG00000006014 CACP,DOL54,JCAP,...
## ENSMUSG00000026822 24p3,AW212229,NRL,...
## REFSEQ
## <list>
## ENSMUSG00000049093 NM_144548,NP_653131
## ENSMUSG00000027656 NM_016873,NP_058569,XM_006499169,...
## ENSMUSG00000037370 NM_001308327,NM_001308329,NM_008813,...
## ENSMUSG00000018830 NM_001161775,NM_013607,NP_001155247,...
## ENSMUSG00000006014 NM_001110146,NM_021400,NP_001103616,...
## ENSMUSG00000026822 NM_008491,NP_032517
## ACCNUM
## <list>
## ENSMUSG00000049093 AAI12426,AAM44230,AF461423,...
## ENSMUSG00000027656 AAC96320,AAD18058,AAH32877,...
## ENSMUSG00000037370 AAA39892,AAA39893,AAI60371,...
## ENSMUSG00000018830 AAA67552,AAB36168,AAH26142,...
## ENSMUSG00000006014 AAI30022,AB034730,AK132597,...
## ENSMUSG00000026822 AAA79309,AAI32070,AAI32072,...
Session Info
sessionInfo()
## R version 3.3.3 (2017-03-06)
## Platform: x86_64-apple-darwin13.4.0 (64-bit)
## Running under: macOS Sierra 10.12.6
##
## locale:
## [1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
##
## attached base packages:
## [1] parallel stats4 stats graphics grDevices utils datasets
## [8] methods base
##
## other attached packages:
## [1] org.Mm.eg.db_3.4.0 AnnotationDbi_1.36.2
## [3] BiocInstaller_1.24.0 viridis_0.5.1
## [5] viridisLite_0.3.0 ggrepel_0.8.0
## [7] data.table_1.11.4 genefilter_1.56.0
## [9] RColorBrewer_1.1-2 gplots_3.0.1
## [11] DESeq2_1.14.1 SummarizedExperiment_1.4.0
## [13] Biobase_2.34.0 GenomicRanges_1.26.4
## [15] GenomeInfoDb_1.10.3 IRanges_2.8.2
## [17] S4Vectors_0.12.2 BiocGenerics_0.20.0
## [19] openxlsx_4.1.0 reshape2_1.4.3
## [21] ggplot2_3.0.0 stringr_1.3.1
## [23] dplyr_0.7.6
##
## loaded via a namespace (and not attached):
## [1] bit64_0.9-7 splines_3.3.3 gtools_3.8.1
## [4] Formula_1.2-3 assertthat_0.2.0 latticeExtra_0.6-28
## [7] blob_1.1.1 yaml_2.2.0 pillar_1.3.0
## [10] RSQLite_2.1.1 backports_1.1.2 lattice_0.20-35
## [13] glue_1.3.0 digest_0.6.15 XVector_0.14.1
## [16] checkmate_1.8.5 colorspace_1.3-2 htmltools_0.3.6
## [19] Matrix_1.2-8 plyr_1.8.4 XML_3.98-1.12
## [22] pkgconfig_2.0.1 zlibbioc_1.20.0 purrr_0.2.5
## [25] xtable_1.8-2 scales_0.5.0 gdata_2.18.0
## [28] BiocParallel_1.8.2 tibble_1.4.2 htmlTable_1.12
## [31] annotate_1.52.1 withr_2.1.2 nnet_7.3-12
## [34] lazyeval_0.2.1 survival_2.42-6 magrittr_1.5
## [37] crayon_1.3.4 memoise_1.1.0 evaluate_0.11
## [40] foreign_0.8-71 tools_3.3.3 locfit_1.5-9.1
## [43] munsell_0.5.0 cluster_2.0.5 zip_1.0.0
## [46] bindrcpp_0.2.2 caTools_1.17.1.1 rlang_0.2.1
## [49] grid_3.3.3 RCurl_1.95-4.11 rstudioapi_0.7
## [52] htmlwidgets_1.2 bitops_1.0-6 base64enc_0.1-3
## [55] rmarkdown_1.10 gtable_0.2.0 DBI_1.0.0
## [58] R6_2.2.2 gridExtra_2.3 knitr_1.20
## [61] bit_1.1-14 bindr_0.1.1 Hmisc_4.1-1
## [64] rprojroot_1.3-2 KernSmooth_2.23-15 stringi_1.2.4
## [67] Rcpp_0.12.18 geneplotter_1.52.0 rpart_4.1-13
## [70] acepack_1.4.1 tidyselect_0.2.4